© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195496
    Prev
    Next
    INDEX
    Explanations

    Schedule, Annexure, Appendix, Letter

    np_acts-logits-general · gemini-2.5-flash-lite

    Proust's masterpiece

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日
    0.48
    +
    0.47
    日下午
    0.46
    日在
    0.46
    '
    0.45
     kezd
    0.45
    ي
    0.44
    ແ
    0.44
    朝
    0.44
    波
    0.43
    POSITIVE LOGITS
    iversary
    0.50
    corrected
    0.49
    चणी
    0.49
    anticipated
    0.49
    ens
    0.48
    etails
    0.48
    вих
    0.47
    orsement
    0.47
    нія
    0.47
    resulting
    0.47
    Activations Density 0.001%

    No Known Activations